© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13147
    Prev
    Next
    INDEX
    Explanations

    references to programming and flight simulation software

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -1.03
    脚注の使い方
    -0.98
    帖最后由
    -0.97
    IsContent
    -0.97
    ⓧ
    -0.95
    DIPSETTING
    -0.93
    FunctionFlags
    -0.91
    contentLoaded
    -0.90
    sizeCache
    -0.90
    InjectAttribute
    -0.90
    POSITIVE LOGITS
    er
    0.48
     secco
    0.47
     vettoriale
    0.45
     secos
    0.45
    y
    0.43
     Vergine
    0.43
    くれる
    0.41
    us
    0.39
    ide
    0.39
     another
    0.39
    Activations Density 1.538%

    No Known Activations